Dr. Oscar A. Jimenez-del-Toro Profile

Dr. Oscar A. Jimenez-del-Toro

at MedGIFT

SPIE Involvement:

Author

Publications (5)

Proceedings Article | 16 March 2020 Presentation + Paper

Systematic comparison of deep learning strategies for weakly supervised Gleason grading

Sebastian Otálora, Manfredo Atzori, Amjad Khan, Oscar Jimenez-del-Toro, Vincent Andrearczyk, Henning Müller

Proceedings Volume 11320, 113200L (2020) https://doi.org/10.1117/12.2548571

KEYWORDS: Data modeling, Performance modeling, Pathology, Principal component analysis, Tissues, Cancer, Biopsy, Machine learning, Feature extraction, Prostate

Read Abstract +

Proceedings Article | 2 March 2020 Presentation + Paper

Exploiting biomedical literature to mine out a large multimodal dataset of rare cancer studies

Anjani Dhrangadhariya, Oscar Jimenez-del-Toro, Vincent Andrearczyk, Manfredo Atzori, Henning Müller

Proceedings Volume 11318, 113180A (2020) https://doi.org/10.1117/12.2549565

KEYWORDS: Cancer, Visualization, Image classification, Mining, Biomedical optics, Microscopy, Tumor growth modeling, Machine learning, Data modeling, Lawrencium

Read Abstract +

Proceedings Article | 6 March 2018 Paper

Tumor proliferation assessment of whole slide images

Mikael Rousson, Martin Hedlund, Mats Andersson, Ludwig Jacobsson, Gunnar Lathen, Bjorn Norell, Oscar Jimenez-del-Toro, Henning Mueller, Manfredo Atzori

Proceedings Volume 10581, 105810Y (2018) https://doi.org/10.1117/12.2293634

KEYWORDS: Detection and tracking algorithms, Pathology, Algorithm development, Breast cancer, Network architectures, Data modeling, Image segmentation, Image classification

Read Abstract +

Proceedings Article | 1 March 2017 Paper

Convolutional neural networks for an automatic classification of prostate tissue slides with high-grade Gleason score

Oscar Jiménez del Toro, Manfredo Atzori, Sebastian Otálora, Mats Andersson, Kristian Eurén, Martin Hedlund, Peter Rönnquist, Henning Müller

Proceedings Volume 10140, 101400O (2017) https://doi.org/10.1117/12.2255710

KEYWORDS: Convolutional neural networks, Image classification, Neural networks, Prostate, Tissues, RGB color model, Data modeling, Prostate cancer, Pathology, Image analysis, Information visualization, Cancer, Visualization, Tumors, Image segmentation

Read Abstract +

The Gleason grading system was developed for assessing prostate histopathology slides. It is correlated to the outcome and incidence of relapse in prostate cancer. Although this grading is part of a standard protocol performed by pathologists, visual inspection of whole slide images (WSIs) has an inherent subjectivity when evaluated by different pathologists. Computer aided pathology has been proposed to generate an objective and reproducible assessment that can help pathologists in their evaluation of new tissue samples. Deep convolutional neural networks are a promising approach for the automatic classification of histopathology images and can hierarchically learn subtle visual features from the data. However, a large number of manual annotations from pathologists are commonly required to obtain sufficient statistical generalization when training new models that can evaluate the daily generated large amounts of pathology data. A fully automatic approach that detects prostatectomy WSIs with high–grade Gleason score is proposed. We evaluate the performance of various deep learning architectures training them with patches extracted from automatically generated regions–of–interest rather than from manually segmented ones. Relevant parameters for training the deep learning model such as size and number of patches as well as the inclusion or not of data augmentation are compared between the tested deep learning architectures. 235 prostate tissue WSIs with their pathology report from the publicly available TCGA data set were used. An accuracy of 78% was obtained in a balanced set of 46 unseen test images with different Gleason grades in a 2–class decision: high vs. low Gleason grade. Grades 7–8, which represent the boundary decision of the proposed task, were particularly well classified. The method is scalable to larger data sets with straightforward re–training of the model to include data from multiple sources, scanners and acquisition techniques. Automatically generated heatmaps for theWSIs could be useful for improving the selection of patches when training networks for big data sets and to guide the visual inspection of these images.

Proceedings Article | 20 March 2015 Paper

Texture classification of anatomical structures in CT using a context-free machine learning approach

Oscar Jiménez del Toro, Antonio Foncubierta-Rodríguez, Adrien Depeursinge, Henning Müller

Proceedings Volume 9414, 94140W (2015) https://doi.org/10.1117/12.2082273

KEYWORDS: Visualization, Lung, Bladder, Spleen, Liver, Medical imaging, Information visualization, Visual analytics, Image segmentation, Matrices

Read Abstract +

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years